skills/mtngtools/agents/10-concise/Gen Agent Trust Hub

10-concise

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, data exfiltration, or dangerous command executions were detected. The skill performs a benign text processing task.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input provided by the user.\n
  • Ingestion points: SKILL.md (argument-hint: "text or file to reduce").\n
  • Boundary markers: Absent.\n
  • Capability inventory: None. No subprocess calls, network operations, or file-writing tools are defined in the skill instructions or referenced local files.\n
  • Sanitization: Absent.\n
  • Analysis: While the skill ingests external data, it lacks the tools or capabilities to perform actions that could harm the environment, even if the input contained malicious instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 01:30 PM
Security Audit — agent-trust-hub — 10-concise